Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this a safe read (readOnly, idempotent, non-destructive), so the description only needs incremental value — and it delivers a real caveat: UPRP does not publish NIP, so owners are matched by company name and city, which warns the agent that matching may be inexact. It stops short of stating whether partial matches or misspellings degrade results, and the 'nip (preferred)' schema hint sits uneasily beside the name/city matching note.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the purpose and then the field inventory and identification guidance. The return-field enumeration is dense but earns its place since there is no output schema; nothing is redundant boilerplate.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-optional-parameter, no-output-schema, read-only lookup tool, the description covers what the tool returns, how ownership is determined, and how to identify the company. Missing only edge behavior (pagination, no-match results, whether name alone is sufficient) which keeps it from a 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, giving a baseline of 3, but the description adds meaning beyond the one-line schema entries by explaining the intended identifier hierarchy (name, KRS, or NIP) and the underlying limitation that drives name-based lookup. It still doesn't clarify whether the 3 optional parameters are mutually exclusive or combinable.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Get Polish Patent Office (UPRP) trademarks owned or applied for by the company') and enumerates the returned data (mark name, application number, Nice classes, status, filing/registration/expiry dates, counts). No sibling tool covers trademarks, so it is trivially distinguishable from the rest of the get_company_* family.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It tells the agent how to identify the company ('by name, KRS, or NIP') and notes that matching is name+city based, which is useful context for calling it. However, it never says when to prefer this over alternatives such as get_company, whether the company must exist first, or what happens if KRS/NIP are unknown beyond falling back to name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.